Driver.java

package driver;

import java.io.IOException;

import mapper.NormalMapper;

import org.apache.hadoop.fs.Path;


import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapred.FileInputFormat;

import org.apache.hadoop.mapred.FileOutputFormat;

import org.apache.hadoop.mapred.JobClient;

import org.apache.hadoop.mapred.JobConf;

import data.Conf;

import data.Record;

import reducer.NormalReducer;

/**
* Driver of NormalJoin(or BasicJoin)
* 
* Implements JoinDriver interface
* 
*/
public class NormalJoin implements JoinDriver{


public static void main(String[] args) throws ClassNotFoundException,
        IOException, InterruptedException {
    if (args.length != 3) {
        System.err
                .println("Usage: Join <left-side table path> <right-side table path> <output path>");
        System.exit(-1);
    }
    String userDir = System.getProperty("user.dir");
    Conf conf = new Conf();
    if (!conf.loadConf(userDir + "/conf.properties")) { // TODO
        System.err.println("Failed in loading configuration file, exit");
        System.exit(-2);
    }

    new NormalJoin().join(args, conf);
}

public void join(String[] args, Conf conf) throws IOException {
    JobConf job = new JobConf(NormalJoin.class);
    job.setJobName("Equal Join");

    Path inLeft = new Path(args[0]);
    Path inRight = new Path(args[1]);
    Path out = new Path(args[2]);

    FileInputFormat.addInputPath(job, inLeft);
    FileInputFormat.addInputPath(job, inRight);
    FileOutputFormat.setOutputPath(job, out);

    job.setMapperClass(NormalMapper.class);
    job.setReducerClass(NormalReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setMapOutputValueClass(Record.class);

    // configuration
    job.set("inputNameLeft", inLeft.toString());
    job.set("mapred.textoutputformat.separator", conf.separator);
    job.setBoolean("mapred.conf.eliminateDuplicate", conf.eliminateDuplicate);

    JobClient.runJob(job);
}

这是我生成的控制台输出，它正在生成一个空输出文件

15/08/03 04:29:47 INFO Configuration.deprecation: 
mapred.textoutputformat.separator is deprecated. Instead, use 
mapreduce.output.textoutputformat.separator

15/08/03 04:29:47 INFO client.RMProxy: Connecting to ResourceManager at /0.0.0.0:8032
15/08/03 04:29:47 INFO client.RMProxy: Connecting to ResourceManager at /0.0.0.0:8032
15/08/03 04:29:48 WARN mapreduce.JobSubmitter: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
15/08/03 04:29:50 INFO mapred.FileInputFormat: Total input paths to process : 2
15/08/03 04:29:50 INFO mapreduce.JobSubmitter: number of splits:3

15/08/03 04:29:50 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1437465092759_0002

15/08/03 04:29:51 INFO impl.YarnClientImpl: Submitted application application_1437465092759_0002

15/08/03 04:29:51 INFO mapreduce.Job: The url to track the job: http://quickstart.cloudera:8088/proxy/application_1437465092759_0002/


15/08/03 04:29:51 INFO mapreduce.Job: Running job: job_1437465092759_0002

15/08/03 04:30:04 INFO mapreduce.Job: Job job_1437465092759_0002 running in uber mode : false

15/08/03 04:30:04 INFO mapreduce.Job:  map 0% reduce 0%

15/08/03 04:30:20 INFO mapreduce.Job:  map 33% reduce 0%

15/08/03 04:30:22 INFO mapreduce.Job:  map 67% reduce 0%


15/08/03 04:30:23 INFO mapreduce.Job:  map 100% reduce 0%

15/08/03 04:30:28 INFO mapreduce.Job:  map 100% reduce 100%

15/08/03 04:30:28 INFO mapreduce.Job: Job job_1437465092759_0002 completed successfully

15/08/03 04:30:28 INFO mapreduce.Job: Counters: 49

File System Counters

    FILE: Number of bytes read=5768091

    FILE: Number of bytes written=11979199

    FILE: Number of read operations=0

    FILE: Number of large read operations=0

    FILE: Number of write operations=0

    HDFS: Number of bytes read=5283057

    HDFS: Number of bytes written=0

    HDFS: Number of read operations=12

    HDFS: Number of large read operations=0

    HDFS: Number of write operations=2

Job Counters 

    Launched map tasks=3


    Launched reduce tasks=1

    Data-local map tasks=3

    Total time spent by all maps in occupied slots (ms)=44449

    Total time spent by all reduces in occupied slots (ms)=5532

    Total time spent by all map tasks (ms)=44449

    Total time spent by all reduce tasks (ms)=5532

    Total vcore-seconds taken by all map tasks=44449

    Total vcore-seconds taken by all reduce tasks=5532

    Total megabyte-seconds taken by all map tasks=45515776

    Total megabyte-seconds taken by all reduce tasks=5664768

Map-Reduce Framework

    Map input records=69495

    Map output records=69495

    Map output bytes=5629095

    Map output materialized bytes=5768103

    Input split bytes=327

    Combine input records=0

    Combine output records=0

    Reduce input groups=55273

    Reduce shuffle bytes=5768103

    Reduce input records=69495

    Reduce output records=0

    Spilled Records=138990

    Shuffled Maps =3

    Failed Shuffles=0

    Merged Map outputs=3

    GC time elapsed (ms)=672

    CPU time spent (ms)=4400

    Physical memory (bytes) snapshot=805781504

    Virtual memory (bytes) snapshot=6027804672

    Total committed heap usage (bytes)=557592576

Shuffle Errors

    BAD_ID=0

    CONNECTION=0

    IO_ERROR=0

    WRONG_LENGTH=0

    WRONG_MAP=0

    WRONG_REDUCE=0

File Input Format Counters 


    Bytes Read=5282730

File Output Format Counters 

    Bytes Written=0

最佳答案

您在程序中使用了旧的 API

mapred.textoutputformat.separator

尝试使用

mapreduce.output.textoutputformat.separator

hadoop.mapred vs hadoop.mapreduce?

同时发布你的代码

关于java - Hadoop 在命令行上执行时生成空输出文件，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/31786380/